fastai2-coursev4-sagemaker-cf.yml

Description: "Creates the SageMaker resources to run the fast.ai v4 (2020) course on a SageMaker notebook instance."

Parameters:
  NotebookName:
    Type: String
    Default: fastai2
    Description: Enter the name of the SageMaker notebook instance. Deafault is fastai2.

  InstanceType:
    Type: String
    Default: ml.p2.xlarge
    AllowedValues:
      - ml.p2.xlarge
      - ml.p3.2xlarge
    Description: Enter ml.p2.xlarge or ml.p3.2xlarge. Default is ml.p2.xlarge.

  VolumeSize:
    Type: Number
    Default: 50
    MinValue: 5
    MaxValue: 16384
    ConstraintDescription: Must be an integer between 5 (GB) and 16384 (16 TB).
    Description: Enter the size of the EBS volume in GB.

Resources:
  SageMakerIamRole:
    Type: "AWS::IAM::Role"
    Properties:
      AssumeRolePolicyDocument:
        Version: "2012-10-17"
        Statement:
          -
            Effect: Allow
            Principal:
              Service: sagemaker.amazonaws.com
            Action: sts:AssumeRole
      Path: "/"
      ManagedPolicyArns:
        - "arn:aws:iam::aws:policy/AmazonSageMakerFullAccess"
      
  FastaiNbLifecycleConfig:
    Type: "AWS::SageMaker::NotebookInstanceLifecycleConfig"
    Properties:
      OnCreate:
        - Content:
            Fn::Base64: |
              #!/bin/bash
              sudo -H -i -u ec2-user bash << EOF
              # create symlinks to EBS volume
              echo "Creating symlinks"
              mkdir /home/ec2-user/SageMaker/.torch && ln -s /home/ec2-user/SageMaker/.torch /home/ec2-user/.torch
              mkdir /home/ec2-user/SageMaker/.fastai && ln -s /home/ec2-user/SageMaker/.fastai /home/ec2-user/.fastai

              # clone the course notebooks
              echo "Clone the course repo"
              git clone https://github.com/fastai/course-v4.git /home/ec2-user/SageMaker/course-v4

              echo "Finished running onCreate script"
              EOF
                
      OnStart:
        - Content:
            Fn::Base64: |
              #!/bin/bash

              sudo -H -i -u ec2-user bash << EOF
              echo "Creating symlinks"
              [ ! -L "/home/ec2-user/.torch" ] && ln -s /home/ec2-user/SageMaker/.torch /home/ec2-user/.torch
              [ ! -L "/home/ec2-user/.fastai" ] && ln -s /home/ec2-user/SageMaker/.fastai /home/ec2-user/.fastai

              echo "install fastai dependencies https://github.com/fastai/fastai2"
              conda install -y -c fastai -c pytorch fastai

              echo "Install a new kernel for fastai with name 'Python 3'"
              python -m ipykernel install --name 'fastai' --display-name 'Python 3' --user

              # uncomment if you want to update PyTorch on every start
              #echo "Update PyTorch library"
              #conda install -y pytorch torchvision -c pytorch

              echo "Update fastai library"
              pip install fastai2

              echo "Install the deps for the course"
              pip install fastai2>=0.0.11 graphviz ipywidgets matplotlib nbdev>=0.2.12 pandas scikit_learn azure-cognitiveservices-search-imagesearch sentencepiece

              echo "Install jupyter nbextension"
              source /home/ec2-user/anaconda3/bin/activate JupyterSystemEnv
              pip install jupyter_contrib_nbextensions
              jupyter contrib nbextensions install --user

              echo "Restarting jupyter notebook server"
              pkill -f jupyter-notebook

              echo "Getting latest version of fastai course"
              cd /home/ec2-user/SageMaker/course-v4
              git pull

              echo "Finished running onStart script"
              EOF

  FastaiNotebookInstance:
    Type: "AWS::SageMaker::NotebookInstance"
    Properties:
      InstanceType: !Ref InstanceType
      LifecycleConfigName: !GetAtt FastaiNbLifecycleConfig.NotebookInstanceLifecycleConfigName
      NotebookInstanceName: !Ref NotebookName
      RoleArn: !GetAtt SageMakerIamRole.Arn
      VolumeSizeInGB: !Ref VolumeSize